SantoshAgastyaraju_SVAP_Asmt_R3

This case study is Monthly production central statistics of food and beverages from year 1997-2011. The data is in the csv format.

Step-1: Frame the Problem: Identify the key question are you trying to answer

Plot the interactive plots for the data set.

Step-2: Acquire the Data: Get the dataset to answer the question.

Acquire the data from the csv file and load it.

setwd="F:\\GLIMS-PGPBDA\\Assignments\\SVAP-Assignment\\Assignment-3\\"
rawdata = read.csv("Production-Department_of_Agriculture_and_Cooperation_1.csv")
str(rawdata)

'data.frame':   429 obs. of  25 variables:
 $ Particulars: Factor w/ 429 levels "(DC)Agricultural Coverage Under Irrigation",..: 8 109 119 121 140 141 226 106 107 108 ...
 $ Frequency  : Factor w/ 1 level "Annual, Ending mar Of Each Year": 1 1 1 1 1 1 1 1 1 1 ...
 $ Unit       : Factor w/ 7 levels "%","Bale mn",..: 5 5 5 5 5 5 5 5 5 5 ...
 $ X3.1993    : int  NA NA NA NA NA NA NA NA NA NA ...
 $ X3.1994    : int  NA NA NA NA NA NA NA NA NA NA ...
 $ X3.1995    : int  NA NA NA NA NA NA NA NA NA NA ...
 $ X3.1996    : num  NA NA NA NA NA NA NA NA NA NA ...
 $ X3.1997    : num  NA NA NA NA NA NA NA NA NA NA ...
 $ X3.1998    : num  NA NA NA NA NA NA NA NA NA NA ...
 $ X3.1999    : num  NA NA NA NA NA NA NA NA NA NA ...
 $ X3.2000    : num  NA NA NA NA NA NA NA NA NA NA ...
 $ X3.2001    : num  NA NA NA NA NA NA NA NA NA NA ...
 $ X3.2002    : num  NA NA NA NA NA NA NA NA NA NA ...
 $ X3.2003    : num  NA NA NA NA NA NA NA NA NA NA ...
 $ X3.2004    : num  NA NA NA NA NA NA NA NA NA NA ...
 $ X3.2005    : num  198.4 103.3 95.1 83.1 72.2 ...
 $ X3.2006    : num  208.6 109.9 98.7 91.8 78.3 ...
 $ X3.2007    : num  217.3 110.6 106.7 93.4 80.2 ...
 $ X3.2008    : num  230.8 121 109.8 96.7 82.7 ...
 $ X3.2009    : num  234.5 118.1 116.3 99.2 84.9 ...
 $ X3.2010    : num  218.1 104 114.2 89.1 75.9 ...
 $ X3.2011    : num  244.5 120.9 123.6 96 80.7 ...
 $ X3.2012    : num  259.3 131.3 128 105.3 92.8 ...
 $ X3.2013    : num  257.1 128.1 129.1 105.2 92.4 ...
 $ X3.2014    : num  264 129 135 106 92 ...

Step-3: Refine the Data: Do the basic refinement to clean up the dataset.

Have only the data related to area wise food grain production

library(tidyr)
rawdata = rawdata[grepl('Agricultural Production Foodgrains Area ',rawdata$Particulars),]
rawdata = rawdata[!grepl('Agricultural Production Foodgrains Area 5 Yr',rawdata$Particulars),]
rawdata = rawdata[,-2:-14]
str(rawdata)

'data.frame':   18 obs. of  12 variables:
 $ Particulars: Factor w/ 429 levels "(DC)Agricultural Coverage Under Irrigation",..: 10 11 12 13 14 15 16 17 18 19 ...
 $ X3.2004    : num  6.81 2.74 7.01 5.07 4.03 ...
 $ X3.2005    : num  6.27 2.58 6.46 5.13 3.72 ...
 $ X3.2006    : num  7.17 2.6 6.55 5.15 3.97 ...
 $ X3.2007    : num  7.27 2.38 6.7 5.06 4.57 ...
 $ X3.2008    : num  7.39 2.52 7.03 5.08 4.48 ...
 $ X3.2009    : num  7.44 2.67 6.92 4.96 4.06 ...
 $ X3.2010    : num  6.67 2.7 6.63 4.86 3.69 ...
 $ X3.2011    : num  8.03 2.77 6.24 4.96 4.53 ...
 $ X3.2012    : num  7.29 2.74 6.7 4.96 4.74 ...
 $ X3.2013    : num  6.85 2.52 6.71 5.04 3.68 ...
 $ X3.2014    : num  NA NA NA NA NA NA NA NA NA NA ...

Step-4: Transform the Data: Do the transformation needed for the dataset.

Do the following transformations in the data. Split the Particulars column name and have the State in seperate column

library(splitstackshape)
rawdata$Particulars = as.character(rawdata$Particulars)
rawdata = cSplit(rawdata, "Particulars", " ")
rawdata = rawdata[ , -c("Particulars_1","Particulars_2","Particulars_3","Particulars_4")]
 rawdata$State = paste(rawdata$Particulars_5,rawdata$Particulars_6)
 rawdata = rawdata[ , -c("Particulars_5","Particulars_6","X3.2014")]
 rawdata$State = sub("NA","",rawdata$State)
 
 rawdata$TotalStats = rawdata$X3.2004+rawdata$X3.2005+rawdata$X3.2006+rawdata$X3.2007+rawdata$X3.2008+rawdata$X3.2009+rawdata$X3.2010+rawdata$X3.2011+rawdata$X3.2012+rawdata$X3.2013
 rawdata

Step-5: Explore the Data: Create the 3 - 4 individual visualisation that explore the dataset.

Exploring the data by creating the visualisations

library(ggplot2)
library(plotly)
library(knitr)
library(DT)
ggplot(rawdata) + aes(rawdata$State,weight = rawdata$X3.2004 , color = rawdata$State) + geom_bar()

ggplot(rawdata) + aes(rawdata$State,weight = rawdata$X3.2005) + geom_bar()

ggplot(rawdata) + aes(rawdata$State,weight = rawdata$X3.2006) + geom_bar()

ggplot(rawdata) + aes(rawdata$State,weight = rawdata$X3.2007) + geom_bar()

ggplot(rawdata) + aes(rawdata$State,weight = rawdata$X3.2008) + geom_bar()

ggplot(rawdata) + aes(rawdata$State,weight = rawdata$X3.2009) + geom_bar()

ggplot(rawdata) + aes(rawdata$State,weight = rawdata$X3.2010) + geom_bar()

ggplot(rawdata) + aes(rawdata$State,weight = rawdata$X3.2011) + geom_bar()

ggplot(rawdata) + aes(rawdata$State,weight = rawdata$X3.2012) + geom_bar()

ggplot(rawdata) + aes(rawdata$State,weight = rawdata$X3.2013) + geom_bar()

ggplot(rawdata) + aes(rawdata$State,weight = rawdata$TotalStats) + geom_bar()

datatable(rawdata,option = list(pagelength = 5))

library(ggplot2)
plot1 = ggplot(rawdata) + aes(rawdata$State,rawdata$TotalStats , color=rawdata$State ) + geom_point()
library(plotly)
ggplotly(plot1)

library(crosstalk)
library(d3scatter)
shared_rawdata <- SharedData$new(rawdata)
bscols(
  list(
    filter_checkbox("State", "StateSelect", shared_rawdata, ~State, inline = TRUE),
    filter_slider("TotalStats", "TotalStats", shared_rawdata, ~TotalStats, width = "100%")
  ),
  d3scatter(shared_rawdata, ~TotalStats, ~X3.2004, ~State, width="100%", height=300),
  d3scatter(shared_rawdata, ~TotalStats, ~X3.2005, ~State, width="100%", height=300)
)

StateSelect

Andhra Pradesh Assam Bihar Chhattisgarh Gujarat Haryana Jharkhand Karnataka Madhya Pradesh Maharashtra Orissa Others Punjab Rajasthan Tamil Nadu Uttar Pradesh Uttaranchal West Bengal

TotalStats